Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    variations of the word "change" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     récon
    -0.87
    достатки
    -0.80
     waard
    -0.79
     juridiques
    -0.77
     bienvenue
    -0.77
     vectoriales
    -0.76
    fifths
    -0.76
     îna
    -0.76
     pitié
    -0.76
    avocat
    -0.75
    POSITIVE LOGITS
     change
    1.90
     changes
    1.87
     Change
    1.82
     CHANGE
    1.73
     Changes
    1.72
    Change
    1.72
    changes
    1.66
    CHANGE
    1.64
     changer
    1.60
    change
    1.58
    Act Density 0.077%

    No Known Activations